Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1918 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1207. Min Act: -0.0002

Data Index: 1089566 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1153. Min Act: -0.0002

Data Index: 105765 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1060785 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1106. Min Act: -0.0002

Data Index: 540248 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0955. Min Act: -0.0002

Data Index: 368615 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0816. Min Act: -0.0002

Data Index: 482113 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0893. Min Act: -0.0002

Data Index: 422480 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1340606 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0832. Min Act: -0.0002

Data Index: 827669 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0807. Min Act: -0.0002

Data Index: 52369 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0799. Min Act: -0.0002

Data Index: 152705 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0764. Min Act: -0.0002

Data Index: 10292 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0781. Min Act: -0.0002

Data Index: 989956 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0693. Min Act: -0.0002

Data Index: 100549 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0794. Min Act: -0.0002

Data Index: 447423 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1266876 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1250052 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0665. Min Act: -0.0002

Data Index: 250688 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0682. Min Act: -0.0002

Data Index: 720879 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0710. Min Act: -0.0002

Data Index: 880482 (C4 (Web Text))

Max Activating Token Index: 292